BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Decision Making under Risk and Uncertainty
DTSTART:20260608T100000
DTEND:20260608T120000
DTSTAMP:20260509T131710Z
UID:9b13797e7886e34393f489f623207ee0b9d7b9e9f26e7adf0551d207
CATEGORIES:Conferences - Seminars
DESCRIPTION:Bo-Yu Yang\nEDIC candidacy exam\nExam president: Prof. Emre Te
 latar\nThesis advisor: Prof. Michael Gastpar\nCo-examiner: Prof. Negar Kiy
 avash\n\nAbstract\nIn real-world decision problems\, human needs can diffe
 r widely in background\, culture\, and objectives\, making it difficult to
  design a single universal value function for agents. To design a model de
 aling with specific tasks\, a natural starting point is to specify an appr
 opriate utility (reward) function and optimize it. However\, in practice\,
  there are many factors that require attention when making decisions. This
  work mainly considers two factors: risk and uncertainty\, and aims to stu
 dy decision making through an information-theoretic lens\, developing algo
 rithms and interpretations for optimizing risk-sensitive utility functions
  under uncertainty.\n\nSelected papers\n1. 1968 - Mossin - Optimal Multipe
 riod Portfolio Policies\nhttps://www.jstor.org/stable/2351447\n\n2. 1984 -
  Cover - An Algorithm for Maximizing Expected Log Investment Return\nhttps
 ://ieeexplore.ieee.org/abstract/document/1056869\n\n3. 2019 - Bleuler-Lapi
 doth-Pfister - Gambling and Rényi Divergence\nhttps://ieeexplore.ieee.org
 /abstract/document/8849800\n 
LOCATION:BC 133 https://plan.epfl.ch/?room==BC%20133
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR